What’s Vulnerable › Vulnerabilities

CVE-2024-42479: llama.cpp allows write-what-where in rpc_server::set_tensor

• Severity: critical (CVSS 9.8 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 2.6% probability of exploitation in the next 30 days
• Public exploit or detection template: yes
• Published: 2024-08-12 · updated 2026-06-17
• Weakness: CWE-123

Description

llama.cpp provides LLM inference in C/C++. The unsafe `data` pointer member in the `rpc_tensor` structure can cause arbitrary address writing. This vulnerability is fixed in b3561.

Affected products

• ggml-org llama.cpp: before b3561 — fixed in b3561

How to fix

Upgrade to a fixed version: ggml-org llama.cpp b3561. Check the vendor advisory for mitigations.

References

• https://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980b
• https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-wcr5-566p-9cwj

Get alerted when CVE-2024-42479 or the next vulnerability affects your stack